The poultry sector is crucial for maintaining food security worldwide. However, many diseases constantly threaten poultry health and can result in significant losses if not controlled. For the detection of poultry diseases, a fine-tuned ConvNeXt V2 model along with a linear classifier is used as to classify poultry disease images. It is trained and tested using a dataset of 6812 images. This model has a test accuracy of 98.97%. This is higher than architectures previously used for poultry disease detection such as a similar size resnet-50 having an accuracy of 97.51%. Consequently, this model for detecting poultry diseases represents a significant advancement in the battle against various poultry diseases.